Christos Chen, M. Guirguis, D. Klein, Donald Brown, Marcel Durietix, Bhiken L. Naik, Christian Ndaribitse
{"title":"Data Pipeline for Digitizing Perioperative Flowsheets from Low Middle Income Countries","authors":"Christos Chen, M. Guirguis, D. Klein, Donald Brown, Marcel Durietix, Bhiken L. Naik, Christian Ndaribitse","doi":"10.1109/sieds55548.2022.9799323","DOIUrl":null,"url":null,"abstract":"In Rwanda and many low-and-middle-income countries (LMIC), surgical, critical care, and anesthesia flowsheets are handwritten by medical professionals due to the lack of digital infrastructure necessary to support digitization systems. Therefore, many LMIC lack macro-level health data that can be utilized to quantify and improve existing healthcare outcomes. Literature has championed post operative mortality rate (POMR) as a key indicator for institutional and national surgical safety [1]. Many surgical operations deemed as “low-risk” in high income countries (HIC) have a surgical mortality rate in LMIC more than ten times that of HIC[2]. Striving to lower POMR in LMIC, the University of Virginia (UVA) is partnering with the University Teaching Hospital of Kigali in Rwanda (CHUK) to digitize anesthesia and intraoperative paper health records. Over the past two years, UVA student capstone teams have contributed in establishing a consistent and reliable system to scan and obtain the surgical flowsheets. The focus of 2021–2022 is to design and implement a data pipeline system that enables Rwandan medical professionals at CHUK to digitize paper surgical flowsheets via a mobile application and receive rapid risk-based notifications. The application enables medical professionals to quickly engage with pertinent perioperative data relevant for improving patient outcomes while also ensuring secure storage of the data, which in turn enables macro-level research for Rwanda's healthcare system. The design presented in this paper enables the user to rapidly upload anesthesia records and receive an email notification regarding hypotension risk data in, on average, 37 seconds. Leveraging AWS storage enables 1000 GB per month and demand-based scaling, dwarfing previous storage capabilities. Compared to the previous system, the average upload time decreased 81.7% from 40 seconds to 7.34 seconds with the usage of the newly designed system. In addition, the new system does not lead to an increase in system failures, where the user is unable to proceed with the usage of the application, which remains at 0% in the newly designed version.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 Systems and Information Engineering Design Symposium (SIEDS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/sieds55548.2022.9799323","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In Rwanda and many low-and-middle-income countries (LMIC), surgical, critical care, and anesthesia flowsheets are handwritten by medical professionals due to the lack of digital infrastructure necessary to support digitization systems. Therefore, many LMIC lack macro-level health data that can be utilized to quantify and improve existing healthcare outcomes. Literature has championed post operative mortality rate (POMR) as a key indicator for institutional and national surgical safety [1]. Many surgical operations deemed as “low-risk” in high income countries (HIC) have a surgical mortality rate in LMIC more than ten times that of HIC[2]. Striving to lower POMR in LMIC, the University of Virginia (UVA) is partnering with the University Teaching Hospital of Kigali in Rwanda (CHUK) to digitize anesthesia and intraoperative paper health records. Over the past two years, UVA student capstone teams have contributed in establishing a consistent and reliable system to scan and obtain the surgical flowsheets. The focus of 2021–2022 is to design and implement a data pipeline system that enables Rwandan medical professionals at CHUK to digitize paper surgical flowsheets via a mobile application and receive rapid risk-based notifications. The application enables medical professionals to quickly engage with pertinent perioperative data relevant for improving patient outcomes while also ensuring secure storage of the data, which in turn enables macro-level research for Rwanda's healthcare system. The design presented in this paper enables the user to rapidly upload anesthesia records and receive an email notification regarding hypotension risk data in, on average, 37 seconds. Leveraging AWS storage enables 1000 GB per month and demand-based scaling, dwarfing previous storage capabilities. Compared to the previous system, the average upload time decreased 81.7% from 40 seconds to 7.34 seconds with the usage of the newly designed system. In addition, the new system does not lead to an increase in system failures, where the user is unable to proceed with the usage of the application, which remains at 0% in the newly designed version.